{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T14:22:27Z","timestamp":1792506147645,"version":"4.5.0"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2018,9,13]],"date-time":"2018-09-13T00:00:00Z","timestamp":1536796800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2018,9,13]],"date-time":"2018-09-13T00:00:00Z","timestamp":1536796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Estimation of mortality risk of very preterm neonates is carried out in clinical and research settings. We aimed at elaborating a prediction tool using machine learning methods. We developed models on a cohort of 23747 neonates &lt;30 weeks gestational age, or &lt;1501 g birth weight, enrolled in the Italian Neonatal Network in 2008\u20132014 (development set), using 12 easily collected perinatal variables. We used a cohort from 2015\u20132016 (N\u2009=\u20095810) as a test set. Among several machine learning methods we chose artificial Neural Networks (NN). The resulting predictor was compared with logistic regression models. In the test cohort, NN had a slightly better discrimination than logistic regression (P\u2009&lt;\u20090.002). The differences were greater in subgroups of neonates (at various gestational age or birth weight intervals, singletons). Using a cutoff of death probability of 0.5, logistic regression misclassified 67\/5810 neonates (1.2 percent) more than NN. In conclusion our study \u2013 the largest published so far \u2013 shows that even in this very simplified scenario, using only limited information available up to 5 minutes after birth, a NN approach had a small but significant advantage over current approaches. The software implementing the predictor is made freely available to the community.<\/jats:p>","DOI":"10.1038\/s41598-018-31920-6","type":"journal-article","created":{"date-parts":[[2018,9,7]],"date-time":"2018-09-07T09:58:13Z","timestamp":1536314293000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":76,"title":["A machine learning approach to estimating preterm infants survival: development of the Preterm Infants Survival Assessment (PISA) predictor"],"prefix":"10.1038","volume":"8","author":[{"given":"Marco","family":"Podda","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5213-2468","authenticated-orcid":false,"given":"Davide","family":"Bacciu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessio","family":"Micheli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roberto","family":"Bell\u00f9","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giulia","family":"Placidi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6074-8975","authenticated-orcid":false,"given":"Luigi","family":"Gagliardi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,9,13]]},"reference":[{"key":"31920_CR1","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1016\/0140-6736(93)92296-6","volume":"342","author":"The International Neonatal Network","year":"1993","unstructured":"The International Neonatal Network. The CRIB (clinical risk index for babies) score: a tool for assessing initial neonatal risk and comparing performance of neonatal intensive care units. Lancet 342, 193\u2013198 (1993).","journal-title":"Lancet"},{"key":"31920_CR2","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1016\/S0140-6736(03)13397-1","volume":"361","author":"G Parry","year":"2003","unstructured":"Parry, G., Tucker, J. & Tarnow-Mordi, W. CRIB II: an update of the Clinical Risk Index for Babies score; UK Neonatal Staffing Study Collaborative Group. Lancet 361, 1789\u201391 (2003).","journal-title":"Lancet"},{"key":"31920_CR3","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1067\/mpd.2001.109608","volume":"138","author":"DK Richardson","year":"2001","unstructured":"Richardson, D. K., Corcoran, J. D., Escobar, G. J. E. & Lee, S. K. SNAP-II and SNAPPE-II: Simplified newborn illness severity and mortality risk scores. J. Pediatr. 138, 92\u2013100 (2001).","journal-title":"J. Pediatr."},{"key":"31920_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0023441","volume":"6","author":"S Medlock","year":"2011","unstructured":"Medlock, S., Ravelli, A. C. J., Tamminga, P., Mol, B. W. M. & Abu-Hanna, A. Prediction of Mortality in Very Premature Infants: A Systematic Review of Prediction Models. PLOS ONE 6, 1\u20139 (2011).","journal-title":"PLOS ONE"},{"issue":"1","key":"31920_CR5","doi-asserted-by":"publisher","first-page":"S68","DOI":"10.1542\/peds.2012-1427h","volume":"131","author":"S Patrick","year":"2013","unstructured":"Patrick, S., Schumacher, R. E. & Davis, M. Methods of Mortality Risk Adjustment in the NICU: A 20-Year Review. Pediatrics. 131(1), S68\u201374 (2013).","journal-title":"Pediatrics."},{"key":"31920_CR6","doi-asserted-by":"publisher","first-page":"1373","DOI":"10.1080\/14767058.2017.1315665","volume":"31","author":"G Bhawandeep","year":"2018","unstructured":"Bhawandeep, G., Deepak, S. & Nazanin, F. Assessment of sickness severity of illness in neonates: review of various neonatal illness scoring systems. J. Matern. Neonat. Med. 31, 1373\u20131380 (2018).","journal-title":"J. Matern. Neonat. Med."},{"key":"31920_CR7","doi-asserted-by":"publisher","first-page":"F419","DOI":"10.1136\/adc.2003.031286","volume":"89","author":"L Gagliardi","year":"2004","unstructured":"Gagliardi, L. et al. Assessing mortality risk in very low birthweight infants: a comparison of CRIB, CRIB-II, and SNAPPE-II. Arch. Dis. Child. Fetal Neonatal Ed. 89, F419\u2013F422 (2004).","journal-title":"Arch. Dis. Child. Fetal Neonatal Ed."},{"key":"31920_CR8","doi-asserted-by":"publisher","first-page":"e156","DOI":"10.1542\/peds.2005-2957","volume":"119","author":"J Zupancic","year":"2007","unstructured":"Zupancic, J. et al. Revalidation of the Score for Neonatal Acute Physiology in the Vermont Oxford Network. Pediatrics. 119, e156\u201363 (2007).","journal-title":"Pediatrics."},{"key":"31920_CR9","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/S0893-6080(01)00111-3","volume":"15","author":"PJG Lisboa","year":"2002","unstructured":"Lisboa, P. J. G. A review of evidence of health benefit from artificial neural networks in medical intervention. Neural Networks 15, 11\u201339 (2002).","journal-title":"Neural Networks"},{"key":"31920_CR10","doi-asserted-by":"publisher","first-page":"F129","DOI":"10.1136\/fn.79.2.F129","volume":"79","author":"B Zernikow","year":"1998","unstructured":"Zernikow, B. et al. Artificial neural network for risk assessment in preterm neonates. Arch. Dis. Child. Fetal Neonatal Ed. 79, F129\u201334 (1998).","journal-title":"Arch. Dis. Child. Fetal Neonatal Ed."},{"key":"31920_CR11","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1016\/S0378-3782(01)00228-6","volume":"65","author":"N Ambalavanan","year":"2001","unstructured":"Ambalavanan, N. & Carlo, W. A. Comparison of the prediction of extremely low birth weight neonatal mortality by regression analysis and by neural networks. Early Hum. Dev. 65, 123\u2013137 (2001).","journal-title":"Early Hum. Dev."},{"key":"31920_CR12","doi-asserted-by":"publisher","first-page":"1367","DOI":"10.1542\/peds.2004-2099","volume":"116","author":"N Ambalavanan","year":"2005","unstructured":"Ambalavanan, N. et al. Prediction of Death for Extremely Low Birth Weight Neonates. Pediatrics. 116, 1367\u20131373 (2005).","journal-title":"Pediatrics."},{"key":"31920_CR13","doi-asserted-by":"crossref","unstructured":"Hastie, T., Tibshirani, R. & Friedman, J. H. The elements of statistical learning: data mining, inference and prediction (Springer, 2009).","DOI":"10.1007\/978-0-387-84858-7"},{"key":"31920_CR14","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman, L. Random Forests. Mach. Learn. 45, 5\u201332 (2001).","journal-title":"Mach. Learn."},{"key":"31920_CR15","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1214\/aos\/1013203451","volume":"29","author":"JH Friedman","year":"2000","unstructured":"Friedman, J. H. Greedy Function Approximation: A Gradient Boosting Machine. Annals. Stat. 29, 1189\u20131232 (2000).","journal-title":"Stat."},{"key":"31920_CR16","doi-asserted-by":"crossref","unstructured":"Shawe-Taylor, J. & Cristianini, N. Kernel Methods for Pattern Analysis (Cambridge University Press, 2004).","DOI":"10.1017\/CBO9780511809682"},{"key":"31920_CR17","unstructured":"Haykin, S. S. Neural Networks and Learning Machines. (Prentice Hall, 2009)."},{"key":"31920_CR18","unstructured":"Goodfellow, I., Bengio, Y. & Courville, A. Deep Learning (MIT Press, 2016)."},{"key":"31920_CR19","unstructured":"Lipton, Z. C. The Mythos of Model Interpretability. CoRR abs\/1606.03490 ICML 2016 Workshop on Human Interpretability in Machine Learning (2016)."},{"key":"31920_CR20","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1148\/radiology.143.1.7063747","volume":"143","author":"JA Hanley","year":"1982","unstructured":"Hanley, J. A. & Mcneil, B. The Meaning and Use of the Area Under a Receiver Operating Characteristic (ROC) Curve. Radiol. 143, 29\u201336 (1982).","journal-title":"Radiol."},{"key":"31920_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1175\/1520-0493(1950)078<0001:VOFEIT>2.0.CO;2","volume":"78","author":"GW Brier","year":"1950","unstructured":"Brier, G. W. Verification of Forecasts Expressed in Terms of Probability. Mon. Weather. Rev. 78, 1\u20133 (1950).","journal-title":"Mon. Weather. Rev."},{"key":"31920_CR22","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F. et al. Scikit-learn: Machine Learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011).","journal-title":"J. Mach. Learn. Res."},{"key":"31920_CR23","doi-asserted-by":"publisher","first-page":"e425","DOI":"10.1542\/peds.2012-2189","volume":"131","author":"BN Manktelow","year":"2013","unstructured":"Manktelow, B. N., Seaton, S. E., Field, D. J. & Draper, E. S. Population-Based Estimates of In-Unit Survival for Very Preterm Infants. Pediatrics. 131, e425\u2013e432 (2013).","journal-title":"Pediatrics."},{"key":"31920_CR24","doi-asserted-by":"publisher","first-page":"1672","DOI":"10.1056\/NEJMoa073059","volume":"358","author":"JE Tyson","year":"2008","unstructured":"Tyson, J. E., Parikh, N. A., Langer, J., Green, C. & Higgins, R. D. Intensive Care for Extreme Prematurity \u2014 Moving beyond Gestational Age. New Engl. J. Medicine 358, 1672\u20131681 (2008).","journal-title":"New Engl. J. Medicine"},{"key":"31920_CR25","doi-asserted-by":"publisher","first-page":"1246","DOI":"10.1542\/peds.2007-0176","volume":"119","author":"L Gagliardi","year":"2007","unstructured":"Gagliardi, L. & Bell\u00f9, R. Score for Neonatal Acute Physiology (SNAP) or Vermont Oxford risk-adjustment model for very low birth weight infants? Pediatrics. 119, 1246\u20131247 (2007).","journal-title":"Pediatrics."},{"key":"31920_CR26","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1067\/mpd.2001.115576","volume":"139","author":"SK Lee","year":"2001","unstructured":"Lee, S. K. et al. Transport risk index of physiologic stability: A practical system for assessing infant transport care. J. Pediatr. 139, 220\u2013226 (2001).","journal-title":"J. Pediatr."},{"key":"31920_CR27","doi-asserted-by":"crossref","unstructured":"Lee, S. K. et al. Transport Risk Index of Physiologic Stability, Version II (TRIPS-II): A Simple and Practical Neonatal Illness Severity Score. Am. J. Perinatol. 30, 395\u2013400 (2013).","DOI":"10.1055\/s-0032-1326983"},{"key":"31920_CR28","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1097\/00003246-199301000-00008","volume":"21","author":"JD Horbar","year":"1993","unstructured":"Horbar, J. D., Onstad, L. & Wright, E. Predicting mortality risk for infants weighing 501 to 1500 grams at birth: a National Institutes of Health Neonatal Research Network report. Critical Care Medicine 21, 12\u201318 (1993).","journal-title":"Critical Care Medicine"},{"key":"31920_CR29","doi-asserted-by":"publisher","first-page":"e154","DOI":"10.1542\/peds.2013-3898","volume":"134","author":"L Gagliardi","year":"2014","unstructured":"Gagliardi, L., Rusconi, F., Bell\u00f9, R. & Zanini, R. Association of Maternal Hypertension and Chorioamnionitis With Preterm Outcomes. Pediatrics. 134, e154\u2013e161 (2014).","journal-title":"Pediatrics."},{"key":"31920_CR30","doi-asserted-by":"crossref","unstructured":"Boghossian, N. S., Geraci, M., Edwards, E. M. & Horbar, J. D. Morbidity and Mortality in Small for Gestational Age Infants at 22 to 29 Weeks\u2019 Gestation. Pediatrics. 141, e20172533 (2018).","DOI":"10.1542\/peds.2017-2533"},{"key":"31920_CR31","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1111\/ppe.12385","volume":"31","author":"L Gagliardi","year":"2017","unstructured":"Gagliardi, L., Lucchini, R., Bell\u00f9, R. & Zanini, R. Antenatal Corticosteroid Prophylaxis in Singleton and Multiple Pregnancies. Paediatr. Perinat. Epidemiol. 31, 394\u2013401 (2017).","journal-title":"Paediatr. Perinat. Epidemiol."},{"key":"31920_CR32","doi-asserted-by":"publisher","first-page":"882","DOI":"10.1093\/aje\/kwh101","volume":"159","author":"MS Pepe","year":"2004","unstructured":"Pepe, M. S., Janes, H., Longton, G., Leisenring, W. & Newcomb, P. Limitations of the Odds Ratio in Gauging the Performance of a Diagnostic, Prognostic, or Screening Marker. Am. J. Epidemiol. 159, 882\u201390 (2004).","journal-title":"Am. J. Epidemiol."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-018-31920-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-018-31920-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-018-31920-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,21]],"date-time":"2022-12-21T09:39:29Z","timestamp":1671615569000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-018-31920-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9,13]]},"references-count":32,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2018,12]]}},"alternative-id":["31920"],"URL":"https:\/\/doi.org\/10.1038\/s41598-018-31920-6","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,9,13]]},"assertion":[{"value":"18 May 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 August 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 September 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}}],"article-number":"13743"}}